March 25 - 29, 2007
Spring Simulation Multiconference 2007 (SpringSim'07)
SCS/SISO Joint Plenary Keynote
Monday March 26, 10:30-12:00
The computing industry has reached an inflection point. Exponential clock speed improvements that have driven computer system performance advances over the last several decades have reached a plateau due to power consumption and heat dissipation constraints. While Moore's Law, which predicts exponentially increasing microelectronic circuit density over time, is expected to continue into the next decade, it is clear that further hardware performance increases will result primarily from multi-core circuits that rely on parallel processing rather than improved clock rates. It is clear that successful exploitation of parallel processing will be critical to achieve sustained growth in computation power in the years ahead. While advanced technologies such as quantum computing offer great long term potential, widespread deployment of such technologies is many years away, and parallel processing will likely remain an important concern even after such new technologies become commercially viable.
These developments will have a profound impact on the modeling and simulation industry. The industry has long relied upon increased computer performance to be able to keep pace with the need to model systems of continually increasing complexity and scale. While the need to simulate larger, more complex systems will continue into the foreseeable future, our ability to simulate such systems with sequential software will be diminishing in the years ahead. Long a "nice to have" capability, parallel simulation will increasingly become a "must have." However, many major hurdles remain before parallel execution can become widely exploited. Development of scalable parallel simulation software, easy to use synchronization techniques, effective load balancing and resource allocation approaches, automated fault tolerance, and time shared use of computing platforms each by itself presents a formidable challenge, yet must all become straightforward or automatic if widespread adoption of parallel simulation methods is to be successful. I will describe some of these challenges and speculate on potential solution approaches that might be deployed to addressing this growing dilemma.
Dr. Richard Fujimoto is Professor and Chair of the Computational
Science and Engineering Division in the College of Computing at the Georgia
Institute of Technology. He received the Ph.D. degree from the University of
California at Berkeley in 1983 in Computer Science and Electrical
Engineering as well as an M.S. degree from UC-Berkeley in 1980, and B.S.
degrees from the University of Illinois at Champaign-Urbana in 1977 and 1978
in Computer Science and Computer Engineering. He has been an active
researcher in the parallel and distributed simulation community since 1985,
and has published numerous technical papers and three books on this topic
and parallel computation. He led the development of parallel/distributed
simulation software systems including the Georgia Tech Time Warp (GTW)
simulation executive and the Federated Simulation Development Kit (FDK),
both of which have been distributed worldwide. Fujimoto led the working
group that defined the time management services for the High Level
Return to SpringSim'07 Home Page
Return to SCS Home Page
Copyright 2007, SCS. All Rights Reserved.